arXiv:2207.05025
공식 코드 · Papers with Code
PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models
원문 초록
We introduce a new synthetic data generator PSP-HDRI$+$ that proves to be a superior pre-training alternative to ImageNet and other large-scale synthetic data counterparts. We demonstrate that pre-training with our synthetic data will yield a more general model that performs better than alternatives even when tested on out-of-distribution (OOD) sets. Furthermore, using ablation studies guided by person keypoint estimation metrics with an off-the-shelf model architecture, we show how to manipulate our synthetic data generator to further improve model performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Monocular 3D Hand Pose Estimation with Implicit Camera Alignment
VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset
AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks
VoxelKP: A Voxel-based Network Architecture for Human Keypoint Estimation in LiDAR Data
BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation
DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.